Introduce end-of-line normalization and add .gitattributes.
Signed-off-by: Thomas Hochstein <thh@inter.net>
This commit is contained in:
Thomas Hochstein
parent
3430c89868
commit
2832c235b2
1
.gitattributes
vendored
Normal file
1
.gitattributes
vendored
Normal file
|
|
@ -0,0 +1 @@
|
||||||
|
* text=auto
|
||||||
454
feedlog.pl
454
feedlog.pl
|
|
@ -1,227 +1,227 @@
|
||||||
#! /usr/bin/perl -W
|
#! /usr/bin/perl -W
|
||||||
#
|
#
|
||||||
# feedlog.pl
|
# feedlog.pl
|
||||||
#
|
#
|
||||||
# This script will log headers and other data to a database
|
# This script will log headers and other data to a database
|
||||||
# for further analysis by parsing a feed from INN.
|
# for further analysis by parsing a feed from INN.
|
||||||
#
|
#
|
||||||
# It is part of the NewsStats package.
|
# It is part of the NewsStats package.
|
||||||
#
|
#
|
||||||
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
#
|
#
|
||||||
# It can be redistributed and/or modified under the same terms under
|
# It can be redistributed and/or modified under the same terms under
|
||||||
# which Perl itself is published.
|
# which Perl itself is published.
|
||||||
|
|
||||||
BEGIN {
|
BEGIN {
|
||||||
our $VERSION = "0.01";
|
our $VERSION = "0.01";
|
||||||
use File::Basename;
|
use File::Basename;
|
||||||
push(@INC, dirname($0));
|
push(@INC, dirname($0));
|
||||||
}
|
}
|
||||||
use strict;
|
use strict;
|
||||||
|
|
||||||
use NewsStats;
|
use NewsStats;
|
||||||
|
|
||||||
use Sys::Syslog qw(:standard :macros);
|
use Sys::Syslog qw(:standard :macros);
|
||||||
|
|
||||||
use Date::Format;
|
use Date::Format;
|
||||||
use DBI;
|
use DBI;
|
||||||
|
|
||||||
################################# Main program #################################
|
################################# Main program #################################
|
||||||
|
|
||||||
### read commandline options
|
### read commandline options
|
||||||
my %Options = &ReadOptions('qd');
|
my %Options = &ReadOptions('qd');
|
||||||
|
|
||||||
### read configuration
|
### read configuration
|
||||||
my %Conf = %{ReadConfig('newsstats.conf')};
|
my %Conf = %{ReadConfig('newsstats.conf')};
|
||||||
|
|
||||||
### init syslog
|
### init syslog
|
||||||
openlog($MySelf, 'nofatal,pid', LOG_NEWS);
|
openlog($MySelf, 'nofatal,pid', LOG_NEWS);
|
||||||
syslog(LOG_NOTICE, "$MyVersion starting up.") if !$Options{'q'};
|
syslog(LOG_NOTICE, "$MyVersion starting up.") if !$Options{'q'};
|
||||||
|
|
||||||
### init database
|
### init database
|
||||||
my $DBHandle = InitDB(\%Conf,0);
|
my $DBHandle = InitDB(\%Conf,0);
|
||||||
if (!$DBHandle) {
|
if (!$DBHandle) {
|
||||||
syslog(LOG_CRIT, 'Database connection failed: %s', $DBI::errstr);
|
syslog(LOG_CRIT, 'Database connection failed: %s', $DBI::errstr);
|
||||||
while (1) {}; # go into endless loop to suppress further errors and respawning
|
while (1) {}; # go into endless loop to suppress further errors and respawning
|
||||||
};
|
};
|
||||||
my $DBQuery = $DBHandle->prepare(sprintf("INSERT INTO %s.%s (day,date,mid,timestamp,token,size,peer,path,newsgroups,headers) VALUES (?,?,?,?,?,?,?,?,?,?)",$Conf{'DBDatabase'},$Conf{'DBTableRaw'}));
|
my $DBQuery = $DBHandle->prepare(sprintf("INSERT INTO %s.%s (day,date,mid,timestamp,token,size,peer,path,newsgroups,headers) VALUES (?,?,?,?,?,?,?,?,?,?)",$Conf{'DBDatabase'},$Conf{'DBTableRaw'}));
|
||||||
|
|
||||||
### main loop
|
### main loop
|
||||||
while (<>) {
|
while (<>) {
|
||||||
chomp;
|
chomp;
|
||||||
# catch empty lines trailing or leading
|
# catch empty lines trailing or leading
|
||||||
if ($_ eq '') {
|
if ($_ eq '') {
|
||||||
next;
|
next;
|
||||||
}
|
}
|
||||||
# first line contains: mid, timestamp, token, size, peer, Path, Newsgroups
|
# first line contains: mid, timestamp, token, size, peer, Path, Newsgroups
|
||||||
my ($Mid, $Timestamp, $Token, $Size, $Peer, $Path, $Newsgroups) = split;
|
my ($Mid, $Timestamp, $Token, $Size, $Peer, $Path, $Newsgroups) = split;
|
||||||
# remaining lines contain headers
|
# remaining lines contain headers
|
||||||
my $Headers = "";
|
my $Headers = "";
|
||||||
while (<>) {
|
while (<>) {
|
||||||
chomp;
|
chomp;
|
||||||
# empty line terminates this article
|
# empty line terminates this article
|
||||||
if ($_ eq '') {
|
if ($_ eq '') {
|
||||||
last;
|
last;
|
||||||
}
|
}
|
||||||
# collect headers
|
# collect headers
|
||||||
$Headers .= $_."\n" ;
|
$Headers .= $_."\n" ;
|
||||||
}
|
}
|
||||||
|
|
||||||
# parse timestamp to day (YYYY-MM-DD) and to MySQL timestamp
|
# parse timestamp to day (YYYY-MM-DD) and to MySQL timestamp
|
||||||
my $Day = time2str("%Y-%m-%d", $Timestamp);
|
my $Day = time2str("%Y-%m-%d", $Timestamp);
|
||||||
my $Date = time2str("%Y-%m-%d %H:%M:%S", $Timestamp);
|
my $Date = time2str("%Y-%m-%d %H:%M:%S", $Timestamp);
|
||||||
|
|
||||||
# write to database
|
# write to database
|
||||||
if (!$DBQuery->execute($Day, $Date, $Mid, $Timestamp, $Token, $Size, $Peer, $Path, $Newsgroups, $Headers)) {
|
if (!$DBQuery->execute($Day, $Date, $Mid, $Timestamp, $Token, $Size, $Peer, $Path, $Newsgroups, $Headers)) {
|
||||||
syslog(LOG_ERR, 'Database error: %s', $DBI::errstr);
|
syslog(LOG_ERR, 'Database error: %s', $DBI::errstr);
|
||||||
};
|
};
|
||||||
$DBQuery->finish;
|
$DBQuery->finish;
|
||||||
|
|
||||||
warn sprintf("-----\nDay: %s\nDate: %s\nMID: %s\nTS: %s\nToken: %s\nSize: %s\nPeer: %s\nPath: %s\nNewsgroups: %s\nHeaders: %s\n",$Day, $Date, $Mid, $Timestamp, $Token, $Size, $Peer, $Path, $Newsgroups, $Headers) if !$Options{'d'};
|
warn sprintf("-----\nDay: %s\nDate: %s\nMID: %s\nTS: %s\nToken: %s\nSize: %s\nPeer: %s\nPath: %s\nNewsgroups: %s\nHeaders: %s\n",$Day, $Date, $Mid, $Timestamp, $Token, $Size, $Peer, $Path, $Newsgroups, $Headers) if !$Options{'d'};
|
||||||
}
|
}
|
||||||
|
|
||||||
### close handles
|
### close handles
|
||||||
$DBHandle->disconnect;
|
$DBHandle->disconnect;
|
||||||
syslog(LOG_NOTICE, "$MySelf closing down.") if !$Options{'q'};
|
syslog(LOG_NOTICE, "$MySelf closing down.") if !$Options{'q'};
|
||||||
closelog();
|
closelog();
|
||||||
|
|
||||||
__END__
|
__END__
|
||||||
|
|
||||||
################################ Documentation #################################
|
################################ Documentation #################################
|
||||||
|
|
||||||
=head1 NAME
|
=head1 NAME
|
||||||
|
|
||||||
feedlog - log data from an INN feed to a database
|
feedlog - log data from an INN feed to a database
|
||||||
|
|
||||||
=head1 SYNOPSIS
|
=head1 SYNOPSIS
|
||||||
|
|
||||||
B<feedlog> [B<-Vhdq>]
|
B<feedlog> [B<-Vhdq>]
|
||||||
|
|
||||||
=head1 REQUIREMENTS
|
=head1 REQUIREMENTS
|
||||||
|
|
||||||
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
Config::Auto
|
Config::Auto
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
Date::Format
|
Date::Format
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
DBI
|
DBI
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 DESCRIPTION
|
=head1 DESCRIPTION
|
||||||
|
|
||||||
This script will log overview data and complete headers to a database
|
This script will log overview data and complete headers to a database
|
||||||
table for further examination by parsing a feed from INN. It will
|
table for further examination by parsing a feed from INN. It will
|
||||||
parse that information and write it to a mysql database table in real
|
parse that information and write it to a mysql database table in real
|
||||||
time.
|
time.
|
||||||
|
|
||||||
All reporting is done to I<syslog> via I<news> facility. If B<feedlog>
|
All reporting is done to I<syslog> via I<news> facility. If B<feedlog>
|
||||||
fails to initiate a database connection at startup, it will log to
|
fails to initiate a database connection at startup, it will log to
|
||||||
I<syslog> with I<CRIT> priority and go in an endless loop, as
|
I<syslog> with I<CRIT> priority and go in an endless loop, as
|
||||||
terminating would only result in a rapid respawn.
|
terminating would only result in a rapid respawn.
|
||||||
|
|
||||||
=head2 Configuration
|
=head2 Configuration
|
||||||
|
|
||||||
F<feedlog.pl> will read its configuration from F<newsstats.conf> which
|
F<feedlog.pl> will read its configuration from F<newsstats.conf> which
|
||||||
should be present in the same directory via Config::Auto.
|
should be present in the same directory via Config::Auto.
|
||||||
|
|
||||||
See doc/INSTALL for an overview of possible configuration options.
|
See doc/INSTALL for an overview of possible configuration options.
|
||||||
|
|
||||||
=head1 OPTIONS
|
=head1 OPTIONS
|
||||||
|
|
||||||
=over 3
|
=over 3
|
||||||
|
|
||||||
=item B<-V> (version)
|
=item B<-V> (version)
|
||||||
|
|
||||||
Print out version and copyright information on B<yapfaq> and exit.
|
Print out version and copyright information on B<yapfaq> and exit.
|
||||||
|
|
||||||
=item B<-h> (help)
|
=item B<-h> (help)
|
||||||
|
|
||||||
Print this man page and exit.
|
Print this man page and exit.
|
||||||
|
|
||||||
=item B<-d> (debug)
|
=item B<-d> (debug)
|
||||||
|
|
||||||
Output debugging information to STDERR while parsing STDIN. You'll
|
Output debugging information to STDERR while parsing STDIN. You'll
|
||||||
find that information most probably in your B<INN> F<errlog> file.
|
find that information most probably in your B<INN> F<errlog> file.
|
||||||
|
|
||||||
=item B<-q> (quiet)
|
=item B<-q> (quiet)
|
||||||
|
|
||||||
Suppress logging to syslog.
|
Suppress logging to syslog.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 INSTALLATION
|
=head1 INSTALLATION
|
||||||
|
|
||||||
See doc/INSTALL.
|
See doc/INSTALL.
|
||||||
|
|
||||||
=head1 EXAMPLES
|
=head1 EXAMPLES
|
||||||
|
|
||||||
Set up a feed like that in your B<INN> F<newsfeeds> file:
|
Set up a feed like that in your B<INN> F<newsfeeds> file:
|
||||||
|
|
||||||
## gather statistics for NewsStats
|
## gather statistics for NewsStats
|
||||||
newsstats!
|
newsstats!
|
||||||
:!*,de.*
|
:!*,de.*
|
||||||
:Tc,WmtfbsPNH,Ac:/path/to/feedlog.pl
|
:Tc,WmtfbsPNH,Ac:/path/to/feedlog.pl
|
||||||
|
|
||||||
See doc/INSTALL for further information.
|
See doc/INSTALL for further information.
|
||||||
|
|
||||||
=head1 FILES
|
=head1 FILES
|
||||||
|
|
||||||
=over 4
|
=over 4
|
||||||
|
|
||||||
=item F<feedlog.pl>
|
=item F<feedlog.pl>
|
||||||
|
|
||||||
The script itself.
|
The script itself.
|
||||||
|
|
||||||
=item F<NewsStats.pm>
|
=item F<NewsStats.pm>
|
||||||
|
|
||||||
Library functions for the NewsStats package.
|
Library functions for the NewsStats package.
|
||||||
|
|
||||||
=item F<newsstats.conf>
|
=item F<newsstats.conf>
|
||||||
|
|
||||||
Runtime configuration file for B<yapfaq>.
|
Runtime configuration file for B<yapfaq>.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 BUGS
|
=head1 BUGS
|
||||||
|
|
||||||
Please report any bugs or feature requests to the author or use the
|
Please report any bugs or feature requests to the author or use the
|
||||||
bug tracker at L<http://bugs.th-h.de/>!
|
bug tracker at L<http://bugs.th-h.de/>!
|
||||||
|
|
||||||
=head1 SEE ALSO
|
=head1 SEE ALSO
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/README
|
doc/README
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/INSTALL
|
doc/INSTALL
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
This script is part of the B<NewsStats> package.
|
This script is part of the B<NewsStats> package.
|
||||||
|
|
||||||
=head1 AUTHOR
|
=head1 AUTHOR
|
||||||
|
|
||||||
Thomas Hochstein <thh@inter.net>
|
Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
=head1 COPYRIGHT AND LICENSE
|
=head1 COPYRIGHT AND LICENSE
|
||||||
|
|
||||||
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
This program is free software; you may redistribute it and/or modify it
|
This program is free software; you may redistribute it and/or modify it
|
||||||
under the same terms as Perl itself.
|
under the same terms as Perl itself.
|
||||||
|
|
||||||
=cut
|
=cut
|
||||||
|
|
|
||||||
624
gatherstats.pl
624
gatherstats.pl
|
|
@ -1,312 +1,312 @@
|
||||||
#! /usr/bin/perl -W
|
#! /usr/bin/perl -W
|
||||||
#
|
#
|
||||||
# gatherstats.pl
|
# gatherstats.pl
|
||||||
#
|
#
|
||||||
# This script will gather statistical information from a database
|
# This script will gather statistical information from a database
|
||||||
# containing headers and other information from a INN feed.
|
# containing headers and other information from a INN feed.
|
||||||
#
|
#
|
||||||
# It is part of the NewsStats package.
|
# It is part of the NewsStats package.
|
||||||
#
|
#
|
||||||
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
#
|
#
|
||||||
# It can be redistributed and/or modified under the same terms under
|
# It can be redistributed and/or modified under the same terms under
|
||||||
# which Perl itself is published.
|
# which Perl itself is published.
|
||||||
|
|
||||||
BEGIN {
|
BEGIN {
|
||||||
our $VERSION = "0.01";
|
our $VERSION = "0.01";
|
||||||
use File::Basename;
|
use File::Basename;
|
||||||
push(@INC, dirname($0));
|
push(@INC, dirname($0));
|
||||||
}
|
}
|
||||||
use strict;
|
use strict;
|
||||||
|
|
||||||
use NewsStats qw(:DEFAULT :TimePeriods ListNewsgroups);
|
use NewsStats qw(:DEFAULT :TimePeriods ListNewsgroups);
|
||||||
|
|
||||||
use DBI;
|
use DBI;
|
||||||
|
|
||||||
################################# Definitions ##################################
|
################################# Definitions ##################################
|
||||||
|
|
||||||
# define types of information that can be gathered
|
# define types of information that can be gathered
|
||||||
# all / groups (/ clients / hosts)
|
# all / groups (/ clients / hosts)
|
||||||
my %LegalTypes;
|
my %LegalTypes;
|
||||||
@LegalTypes{('all','groups')} = ();
|
@LegalTypes{('all','groups')} = ();
|
||||||
|
|
||||||
################################# Main program #################################
|
################################# Main program #################################
|
||||||
|
|
||||||
### read commandline options
|
### read commandline options
|
||||||
my %Options = &ReadOptions('dom:p:t:n:r:g:c:s:');
|
my %Options = &ReadOptions('dom:p:t:n:r:g:c:s:');
|
||||||
|
|
||||||
### read configuration
|
### read configuration
|
||||||
my %Conf = %{ReadConfig('newsstats.conf')};
|
my %Conf = %{ReadConfig('newsstats.conf')};
|
||||||
|
|
||||||
### override configuration via commandline options
|
### override configuration via commandline options
|
||||||
my %ConfOverride;
|
my %ConfOverride;
|
||||||
$ConfOverride{'DBTableRaw'} = $Options{'r'} if $Options{'r'};
|
$ConfOverride{'DBTableRaw'} = $Options{'r'} if $Options{'r'};
|
||||||
$ConfOverride{'DBTableGrps'} = $Options{'g'} if $Options{'g'};
|
$ConfOverride{'DBTableGrps'} = $Options{'g'} if $Options{'g'};
|
||||||
$ConfOverride{'DBTableClnts'} = $Options{'c'} if $Options{'c'};
|
$ConfOverride{'DBTableClnts'} = $Options{'c'} if $Options{'c'};
|
||||||
$ConfOverride{'DBTableHosts'} = $Options{'s'} if $Options{'s'};
|
$ConfOverride{'DBTableHosts'} = $Options{'s'} if $Options{'s'};
|
||||||
$ConfOverride{'TLH'} = $Options{'n'} if $Options{'n'};
|
$ConfOverride{'TLH'} = $Options{'n'} if $Options{'n'};
|
||||||
&OverrideConfig(\%Conf,\%ConfOverride);
|
&OverrideConfig(\%Conf,\%ConfOverride);
|
||||||
|
|
||||||
### get type of information to gather, defaulting to 'all'
|
### get type of information to gather, defaulting to 'all'
|
||||||
$Options{'t'} = 'all' if !$Options{'t'};
|
$Options{'t'} = 'all' if !$Options{'t'};
|
||||||
die "$MySelf: E: Unknown type '-t $Options{'t'}'!\n" if !exists($LegalTypes{$Options{'t'}});
|
die "$MySelf: E: Unknown type '-t $Options{'t'}'!\n" if !exists($LegalTypes{$Options{'t'}});
|
||||||
|
|
||||||
### get time period (-m or -p)
|
### get time period (-m or -p)
|
||||||
my ($StartMonth,$EndMonth) = &GetTimePeriod($Options{'m'},$Options{'p'});
|
my ($StartMonth,$EndMonth) = &GetTimePeriod($Options{'m'},$Options{'p'});
|
||||||
|
|
||||||
### init database
|
### init database
|
||||||
my $DBHandle = InitDB(\%Conf,1);
|
my $DBHandle = InitDB(\%Conf,1);
|
||||||
|
|
||||||
### get data for each month
|
### get data for each month
|
||||||
warn "$MySelf: W: Output only mode. Database is not updated.\n" if $Options{'o'};
|
warn "$MySelf: W: Output only mode. Database is not updated.\n" if $Options{'o'};
|
||||||
foreach my $Month (&ListMonth($StartMonth,$EndMonth)) {
|
foreach my $Month (&ListMonth($StartMonth,$EndMonth)) {
|
||||||
|
|
||||||
print "---------- $Month ----------\n" if $Options{'d'};
|
print "---------- $Month ----------\n" if $Options{'d'};
|
||||||
|
|
||||||
if ($Options{'t'} eq 'all' or $Options{'t'} eq 'groups') {
|
if ($Options{'t'} eq 'all' or $Options{'t'} eq 'groups') {
|
||||||
### ----------------------------------------------
|
### ----------------------------------------------
|
||||||
### get groups data (number of postings per group)
|
### get groups data (number of postings per group)
|
||||||
# get groups data from raw table for given month
|
# get groups data from raw table for given month
|
||||||
my $DBQuery = $DBHandle->prepare(sprintf("SELECT newsgroups FROM %s.%s WHERE day LIKE ? AND NOT disregard",$Conf{'DBDatabase'},$Conf{'DBTableRaw'}));
|
my $DBQuery = $DBHandle->prepare(sprintf("SELECT newsgroups FROM %s.%s WHERE day LIKE ? AND NOT disregard",$Conf{'DBDatabase'},$Conf{'DBTableRaw'}));
|
||||||
$DBQuery->execute($Month.'-%') or die sprintf("$MySelf: E: Can't get groups data for %s from %s.%s: $DBI::errstr\n",$Month,$Conf{'DBDatabase'},$Conf{'DBTableRaw'});
|
$DBQuery->execute($Month.'-%') or die sprintf("$MySelf: E: Can't get groups data for %s from %s.%s: $DBI::errstr\n",$Month,$Conf{'DBDatabase'},$Conf{'DBTableRaw'});
|
||||||
|
|
||||||
# count postings per group
|
# count postings per group
|
||||||
my %Postings;
|
my %Postings;
|
||||||
|
|
||||||
while (($_) = $DBQuery->fetchrow_array) {
|
while (($_) = $DBQuery->fetchrow_array) {
|
||||||
# get list oft newsgroups and hierarchies from Newsgroups:
|
# get list oft newsgroups and hierarchies from Newsgroups:
|
||||||
my %Newsgroups = ListNewsgroups($_);
|
my %Newsgroups = ListNewsgroups($_);
|
||||||
# count each newsgroup and hierarchy once
|
# count each newsgroup and hierarchy once
|
||||||
foreach (sort keys %Newsgroups) {
|
foreach (sort keys %Newsgroups) {
|
||||||
# don't count newsgroup/hierarchy in wrong TLH
|
# don't count newsgroup/hierarchy in wrong TLH
|
||||||
next if(defined($Conf{'TLH'}) and !/^$Conf{'TLH'}/);
|
next if(defined($Conf{'TLH'}) and !/^$Conf{'TLH'}/);
|
||||||
$Postings{$_}++;
|
$Postings{$_}++;
|
||||||
};
|
};
|
||||||
};
|
};
|
||||||
|
|
||||||
print "----- GroupStats -----\n" if $Options{'d'};
|
print "----- GroupStats -----\n" if $Options{'d'};
|
||||||
foreach my $Newsgroup (sort keys %Postings) {
|
foreach my $Newsgroup (sort keys %Postings) {
|
||||||
print "$Newsgroup => $Postings{$Newsgroup}\n" if $Options{'d'};
|
print "$Newsgroup => $Postings{$Newsgroup}\n" if $Options{'d'};
|
||||||
if (!$Options{'o'}) {
|
if (!$Options{'o'}) {
|
||||||
# write to database
|
# write to database
|
||||||
$DBQuery = $DBHandle->prepare(sprintf("REPLACE INTO %s.%s (month,newsgroup,postings) VALUES (?, ?, ?)",$Conf{'DBDatabase'},$Conf{'DBTableGrps'}));
|
$DBQuery = $DBHandle->prepare(sprintf("REPLACE INTO %s.%s (month,newsgroup,postings) VALUES (?, ?, ?)",$Conf{'DBDatabase'},$Conf{'DBTableGrps'}));
|
||||||
$DBQuery->execute($Month, $Newsgroup, $Postings{$Newsgroup}) or die sprintf("$MySelf: E: Can't write groups data for %s/%s to %s.%s: $DBI::errstr\n",$Month,$Newsgroup,$Conf{'DBDatabase'},$Conf{'DBTableGrps'});
|
$DBQuery->execute($Month, $Newsgroup, $Postings{$Newsgroup}) or die sprintf("$MySelf: E: Can't write groups data for %s/%s to %s.%s: $DBI::errstr\n",$Month,$Newsgroup,$Conf{'DBDatabase'},$Conf{'DBTableGrps'});
|
||||||
$DBQuery->finish;
|
$DBQuery->finish;
|
||||||
};
|
};
|
||||||
};
|
};
|
||||||
} else {
|
} else {
|
||||||
# other types of information go here - later on
|
# other types of information go here - later on
|
||||||
};
|
};
|
||||||
};
|
};
|
||||||
|
|
||||||
### close handles
|
### close handles
|
||||||
$DBHandle->disconnect;
|
$DBHandle->disconnect;
|
||||||
|
|
||||||
__END__
|
__END__
|
||||||
|
|
||||||
################################ Documentation #################################
|
################################ Documentation #################################
|
||||||
|
|
||||||
=head1 NAME
|
=head1 NAME
|
||||||
|
|
||||||
gatherstats - process statistical data from a raw source
|
gatherstats - process statistical data from a raw source
|
||||||
|
|
||||||
=head1 SYNOPSIS
|
=head1 SYNOPSIS
|
||||||
|
|
||||||
B<gatherstats> [B<-Vhdo>] [B<-m> I<YYYY-MM>] [B<-p> I<YYYY-MM:YYYY-MM>] [B<-t> I<type>] [B<-n> I<TLH>] [B<-r> I<database table>] [B<-g> I<database table>] [B<-c> I<database table>] [B<-s> I<database table>]
|
B<gatherstats> [B<-Vhdo>] [B<-m> I<YYYY-MM>] [B<-p> I<YYYY-MM:YYYY-MM>] [B<-t> I<type>] [B<-n> I<TLH>] [B<-r> I<database table>] [B<-g> I<database table>] [B<-c> I<database table>] [B<-s> I<database table>]
|
||||||
|
|
||||||
=head1 REQUIREMENTS
|
=head1 REQUIREMENTS
|
||||||
|
|
||||||
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
Config::Auto
|
Config::Auto
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
DBI
|
DBI
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 DESCRIPTION
|
=head1 DESCRIPTION
|
||||||
|
|
||||||
This script will extract and process statistical information from a
|
This script will extract and process statistical information from a
|
||||||
database table which is fed from F<feedlog.pl> for a given time period
|
database table which is fed from F<feedlog.pl> for a given time period
|
||||||
and write its results to (an)other database table(s).
|
and write its results to (an)other database table(s).
|
||||||
|
|
||||||
The time period to act on defaults to last month; you can assign
|
The time period to act on defaults to last month; you can assign
|
||||||
another month via the B<-m> switch or a time period via the B<-p>
|
another month via the B<-m> switch or a time period via the B<-p>
|
||||||
switch; the latter takes preference.
|
switch; the latter takes preference.
|
||||||
|
|
||||||
By default B<gatherstats> will process all types of information; you
|
By default B<gatherstats> will process all types of information; you
|
||||||
can change that using the B<-t> switch and assigning the type of
|
can change that using the B<-t> switch and assigning the type of
|
||||||
information to process. Currently only processing of the number of
|
information to process. Currently only processing of the number of
|
||||||
postings per group per month is implemented anyway, so that doesn't
|
postings per group per month is implemented anyway, so that doesn't
|
||||||
matter yet.
|
matter yet.
|
||||||
|
|
||||||
Possible information types include:
|
Possible information types include:
|
||||||
|
|
||||||
=over 3
|
=over 3
|
||||||
|
|
||||||
=item B<groups> (postings per group per month)
|
=item B<groups> (postings per group per month)
|
||||||
|
|
||||||
B<gatherstats> will examine Newsgroups: headers. Crosspostings will be
|
B<gatherstats> will examine Newsgroups: headers. Crosspostings will be
|
||||||
counted for each single group they appear in. Groups not in I<TLH>
|
counted for each single group they appear in. Groups not in I<TLH>
|
||||||
will be ignored.
|
will be ignored.
|
||||||
|
|
||||||
B<gatherstats> will also add up the number of postings for each
|
B<gatherstats> will also add up the number of postings for each
|
||||||
hierarchy level, but only count each posting once. A posting to
|
hierarchy level, but only count each posting once. A posting to
|
||||||
de.alt.test will be counted for de.alt.test, de.alt.ALL and de.ALL,
|
de.alt.test will be counted for de.alt.test, de.alt.ALL and de.ALL,
|
||||||
respectively. A crossposting to de.alt.test and de.alt.admin, on the
|
respectively. A crossposting to de.alt.test and de.alt.admin, on the
|
||||||
other hand, will be counted for de.alt.test and de.alt.admin each, but
|
other hand, will be counted for de.alt.test and de.alt.admin each, but
|
||||||
only once for de.alt.ALL and de.ALL.
|
only once for de.alt.ALL and de.ALL.
|
||||||
|
|
||||||
Data is written to I<DBTableGrps> (see doc/INSTALL).
|
Data is written to I<DBTableGrps> (see doc/INSTALL).
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head2 Configuration
|
=head2 Configuration
|
||||||
|
|
||||||
F<gatherstats.pl> will read its configuration from F<newsstats.conf>
|
F<gatherstats.pl> will read its configuration from F<newsstats.conf>
|
||||||
which should be present in the same directory via Config::Auto.
|
which should be present in the same directory via Config::Auto.
|
||||||
|
|
||||||
See doc/INSTALL for an overview of possible configuration options.
|
See doc/INSTALL for an overview of possible configuration options.
|
||||||
|
|
||||||
You can override configuration options via the B<-n>, B<-r>, B<-g>,
|
You can override configuration options via the B<-n>, B<-r>, B<-g>,
|
||||||
B<-c> and B<-s> switches, respectively.
|
B<-c> and B<-s> switches, respectively.
|
||||||
|
|
||||||
=head1 OPTIONS
|
=head1 OPTIONS
|
||||||
|
|
||||||
=over 3
|
=over 3
|
||||||
|
|
||||||
=item B<-V> (version)
|
=item B<-V> (version)
|
||||||
|
|
||||||
Print out version and copyright information on B<yapfaq> and exit.
|
Print out version and copyright information on B<yapfaq> and exit.
|
||||||
|
|
||||||
=item B<-h> (help)
|
=item B<-h> (help)
|
||||||
|
|
||||||
Print this man page and exit.
|
Print this man page and exit.
|
||||||
|
|
||||||
=item B<-d> (debug)
|
=item B<-d> (debug)
|
||||||
|
|
||||||
Output debugging information to STDOUT while processing (number of
|
Output debugging information to STDOUT while processing (number of
|
||||||
postings per group).
|
postings per group).
|
||||||
|
|
||||||
=item B<-o> (output only)
|
=item B<-o> (output only)
|
||||||
|
|
||||||
Do not write results to database. You should use B<-d> in conjunction
|
Do not write results to database. You should use B<-d> in conjunction
|
||||||
with B<-o> ... everything else seems a bit pointless.
|
with B<-o> ... everything else seems a bit pointless.
|
||||||
|
|
||||||
=item B<-m> I<YYYY-MM> (month)
|
=item B<-m> I<YYYY-MM> (month)
|
||||||
|
|
||||||
Set processing period to a month in YYYY-MM format. Ignored if B<-p>
|
Set processing period to a month in YYYY-MM format. Ignored if B<-p>
|
||||||
is set.
|
is set.
|
||||||
|
|
||||||
=item B<-p> I<YYYY-MM:YYYY-MM> (period)
|
=item B<-p> I<YYYY-MM:YYYY-MM> (period)
|
||||||
|
|
||||||
Set processing period to a time period between two month, each in
|
Set processing period to a time period between two month, each in
|
||||||
YYYY-MM format, separated by a colon. Overrides B<-m>.
|
YYYY-MM format, separated by a colon. Overrides B<-m>.
|
||||||
|
|
||||||
=item B<-t> I<type> (type)
|
=item B<-t> I<type> (type)
|
||||||
|
|
||||||
Set processing type to one of I<all> and I<groups>. Defaults to all
|
Set processing type to one of I<all> and I<groups>. Defaults to all
|
||||||
(and is currently rather pointless as only I<groups> has been
|
(and is currently rather pointless as only I<groups> has been
|
||||||
implemented).
|
implemented).
|
||||||
|
|
||||||
=item B<-n> I<TLH> (newsgroup hierarchy)
|
=item B<-n> I<TLH> (newsgroup hierarchy)
|
||||||
|
|
||||||
Override I<TLH> from F<newsstats.conf>.
|
Override I<TLH> from F<newsstats.conf>.
|
||||||
|
|
||||||
=item B<-r> I<table> (raw data table)
|
=item B<-r> I<table> (raw data table)
|
||||||
|
|
||||||
Override I<DBTableRaw> from F<newsstats.conf>.
|
Override I<DBTableRaw> from F<newsstats.conf>.
|
||||||
|
|
||||||
=item B<-g> I<table> (postings per group table)
|
=item B<-g> I<table> (postings per group table)
|
||||||
|
|
||||||
Override I<DBTableGrps> from F<newsstats.conf>.
|
Override I<DBTableGrps> from F<newsstats.conf>.
|
||||||
|
|
||||||
=item B<-c> I<table> (client data table)
|
=item B<-c> I<table> (client data table)
|
||||||
|
|
||||||
Override I<DBTableClnts> from F<newsstats.conf>.
|
Override I<DBTableClnts> from F<newsstats.conf>.
|
||||||
|
|
||||||
=item B<-s> I<table> (server/host data table)
|
=item B<-s> I<table> (server/host data table)
|
||||||
|
|
||||||
Override I<DBTableHosts> from F<newsstats.conf>.
|
Override I<DBTableHosts> from F<newsstats.conf>.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 INSTALLATION
|
=head1 INSTALLATION
|
||||||
|
|
||||||
See doc/INSTALL.
|
See doc/INSTALL.
|
||||||
|
|
||||||
=head1 EXAMPLES
|
=head1 EXAMPLES
|
||||||
|
|
||||||
Process all types of information for lasth month:
|
Process all types of information for lasth month:
|
||||||
|
|
||||||
gatherstats
|
gatherstats
|
||||||
|
|
||||||
Do a dry run, showing results of processing:
|
Do a dry run, showing results of processing:
|
||||||
|
|
||||||
gatherstats -do
|
gatherstats -do
|
||||||
|
|
||||||
Process all types of information for January of 2010:
|
Process all types of information for January of 2010:
|
||||||
|
|
||||||
gatherstats -m 2010-01
|
gatherstats -m 2010-01
|
||||||
|
|
||||||
Process only number of postings for the year of 2010:
|
Process only number of postings for the year of 2010:
|
||||||
|
|
||||||
gatherstats -p 2010-01:2010-12 -t groups
|
gatherstats -p 2010-01:2010-12 -t groups
|
||||||
|
|
||||||
=head1 FILES
|
=head1 FILES
|
||||||
|
|
||||||
=over 4
|
=over 4
|
||||||
|
|
||||||
=item F<gatherstats.pl>
|
=item F<gatherstats.pl>
|
||||||
|
|
||||||
The script itself.
|
The script itself.
|
||||||
|
|
||||||
=item F<NewsStats.pm>
|
=item F<NewsStats.pm>
|
||||||
|
|
||||||
Library functions for the NewsStats package.
|
Library functions for the NewsStats package.
|
||||||
|
|
||||||
=item F<newsstats.conf>
|
=item F<newsstats.conf>
|
||||||
|
|
||||||
Runtime configuration file for B<yapfaq>.
|
Runtime configuration file for B<yapfaq>.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 BUGS
|
=head1 BUGS
|
||||||
|
|
||||||
Please report any bugs or feature requests to the author or use the
|
Please report any bugs or feature requests to the author or use the
|
||||||
bug tracker at L<http://bugs.th-h.de/>!
|
bug tracker at L<http://bugs.th-h.de/>!
|
||||||
|
|
||||||
=head1 SEE ALSO
|
=head1 SEE ALSO
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/README
|
doc/README
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/INSTALL
|
doc/INSTALL
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
This script is part of the B<NewsStats> package.
|
This script is part of the B<NewsStats> package.
|
||||||
|
|
||||||
=head1 AUTHOR
|
=head1 AUTHOR
|
||||||
|
|
||||||
Thomas Hochstein <thh@inter.net>
|
Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
=head1 COPYRIGHT AND LICENSE
|
=head1 COPYRIGHT AND LICENSE
|
||||||
|
|
||||||
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
This program is free software; you may redistribute it and/or modify it
|
This program is free software; you may redistribute it and/or modify it
|
||||||
under the same terms as Perl itself.
|
under the same terms as Perl itself.
|
||||||
|
|
||||||
=cut
|
=cut
|
||||||
|
|
|
||||||
950
groupstats.pl
950
groupstats.pl
|
|
@ -1,475 +1,475 @@
|
||||||
#! /usr/bin/perl -W
|
#! /usr/bin/perl -W
|
||||||
#
|
#
|
||||||
# groupstats.pl
|
# groupstats.pl
|
||||||
#
|
#
|
||||||
# This script will get statistical data on newgroup usage
|
# This script will get statistical data on newgroup usage
|
||||||
# form a database.
|
# form a database.
|
||||||
#
|
#
|
||||||
# It is part of the NewsStats package.
|
# It is part of the NewsStats package.
|
||||||
#
|
#
|
||||||
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
#
|
#
|
||||||
# It can be redistributed and/or modified under the same terms under
|
# It can be redistributed and/or modified under the same terms under
|
||||||
# which Perl itself is published.
|
# which Perl itself is published.
|
||||||
|
|
||||||
BEGIN {
|
BEGIN {
|
||||||
our $VERSION = "0.01";
|
our $VERSION = "0.01";
|
||||||
use File::Basename;
|
use File::Basename;
|
||||||
push(@INC, dirname($0));
|
push(@INC, dirname($0));
|
||||||
}
|
}
|
||||||
use strict;
|
use strict;
|
||||||
|
|
||||||
use NewsStats qw(:DEFAULT :TimePeriods :Output :SQLHelper);
|
use NewsStats qw(:DEFAULT :TimePeriods :Output :SQLHelper);
|
||||||
|
|
||||||
use DBI;
|
use DBI;
|
||||||
|
|
||||||
################################# Main program #################################
|
################################# Main program #################################
|
||||||
|
|
||||||
### read commandline options
|
### read commandline options
|
||||||
my %Options = &ReadOptions('m:p:n:o:t:l:b:iscqdg:');
|
my %Options = &ReadOptions('m:p:n:o:t:l:b:iscqdg:');
|
||||||
|
|
||||||
### read configuration
|
### read configuration
|
||||||
my %Conf = %{ReadConfig('newsstats.conf')};
|
my %Conf = %{ReadConfig('newsstats.conf')};
|
||||||
|
|
||||||
### override configuration via commandline options
|
### override configuration via commandline options
|
||||||
my %ConfOverride;
|
my %ConfOverride;
|
||||||
$ConfOverride{'DBTableGrps'} = $Options{'g'} if $Options{'g'};
|
$ConfOverride{'DBTableGrps'} = $Options{'g'} if $Options{'g'};
|
||||||
&OverrideConfig(\%Conf,\%ConfOverride);
|
&OverrideConfig(\%Conf,\%ConfOverride);
|
||||||
|
|
||||||
### check for incompatible command line options
|
### check for incompatible command line options
|
||||||
# you can't mix '-t', '-b' and '-l'
|
# you can't mix '-t', '-b' and '-l'
|
||||||
# -b/-l take preference over -t, and -b takes preference over -l
|
# -b/-l take preference over -t, and -b takes preference over -l
|
||||||
if ($Options{'b'} or $Options{'l'}) {
|
if ($Options{'b'} or $Options{'l'}) {
|
||||||
if ($Options{'t'}) {
|
if ($Options{'t'}) {
|
||||||
# drop -t
|
# drop -t
|
||||||
warn ("$MySelf: W: You cannot combine thresholds (-t) and top lists (-b) or levels (-l). Threshold '-t $Options{'t'}' was ignored.\n");
|
warn ("$MySelf: W: You cannot combine thresholds (-t) and top lists (-b) or levels (-l). Threshold '-t $Options{'t'}' was ignored.\n");
|
||||||
undef($Options{'t'});
|
undef($Options{'t'});
|
||||||
};
|
};
|
||||||
if ($Options{'b'} and $Options{'l'}) {
|
if ($Options{'b'} and $Options{'l'}) {
|
||||||
# drop -l
|
# drop -l
|
||||||
warn ("$MySelf: W: You cannot combine top lists (-b) and levels (-l). Level '-l $Options{'l'}' was ignored.\n");
|
warn ("$MySelf: W: You cannot combine top lists (-b) and levels (-l). Level '-l $Options{'l'}' was ignored.\n");
|
||||||
undef($Options{'l'});
|
undef($Options{'l'});
|
||||||
};
|
};
|
||||||
# -q/-d don't work with -b or -l
|
# -q/-d don't work with -b or -l
|
||||||
warn ("$MySelf: W: Sorting by number of postings (-q) ignored due to top list mode (-b) / levels (-l).\n") if $Options{'q'};
|
warn ("$MySelf: W: Sorting by number of postings (-q) ignored due to top list mode (-b) / levels (-l).\n") if $Options{'q'};
|
||||||
warn ("$MySelf: W: Reverse sorting (-d) ignored due to top list mode (-b) / levels (-l).\n") if $Options{'d'};
|
warn ("$MySelf: W: Reverse sorting (-d) ignored due to top list mode (-b) / levels (-l).\n") if $Options{'d'};
|
||||||
};
|
};
|
||||||
|
|
||||||
### check output type
|
### check output type
|
||||||
# default output type to 'dump'
|
# default output type to 'dump'
|
||||||
$Options{'o'} = 'dump' if !$Options{'o'};
|
$Options{'o'} = 'dump' if !$Options{'o'};
|
||||||
# fail if more than one newsgroup is combined with 'dumpgroup' type
|
# fail if more than one newsgroup is combined with 'dumpgroup' type
|
||||||
die ("$MySelf: E: You cannot combine newsgroup lists (-n) with more than one group with '-o dumpgroup'!\n") if ($Options{'o'} eq 'dumpgroup' and defined($Options{'n'}) and $Options{'n'} =~ /:|\*/);
|
die ("$MySelf: E: You cannot combine newsgroup lists (-n) with more than one group with '-o dumpgroup'!\n") if ($Options{'o'} eq 'dumpgroup' and defined($Options{'n'}) and $Options{'n'} =~ /:|\*/);
|
||||||
# accept 'dumpgroup' only with -n
|
# accept 'dumpgroup' only with -n
|
||||||
if ($Options{'o'} eq 'dumpgroup' and !defined($Options{'n'})) {
|
if ($Options{'o'} eq 'dumpgroup' and !defined($Options{'n'})) {
|
||||||
$Options{'o'} = 'dump';
|
$Options{'o'} = 'dump';
|
||||||
warn ("$MySelf: W: You must submit exactly one newsgroup ('-n news.group') for '-o dumpgroup'. Output type was set to 'dump'.\n");
|
warn ("$MySelf: W: You must submit exactly one newsgroup ('-n news.group') for '-o dumpgroup'. Output type was set to 'dump'.\n");
|
||||||
};
|
};
|
||||||
# set output type to 'pretty' for -l
|
# set output type to 'pretty' for -l
|
||||||
if ($Options{'l'}) {
|
if ($Options{'l'}) {
|
||||||
$Options{'o'} = 'pretty';
|
$Options{'o'} = 'pretty';
|
||||||
warn ("$MySelf: W: Output type forced to '-o pretty' due to usage of '-l'.\n");
|
warn ("$MySelf: W: Output type forced to '-o pretty' due to usage of '-l'.\n");
|
||||||
};
|
};
|
||||||
|
|
||||||
### get time period
|
### get time period
|
||||||
my ($StartMonth,$EndMonth) = &GetTimePeriod($Options{'m'},$Options{'p'});
|
my ($StartMonth,$EndMonth) = &GetTimePeriod($Options{'m'},$Options{'p'});
|
||||||
# reset to one month for 'dump' output type
|
# reset to one month for 'dump' output type
|
||||||
if ($Options{'o'} eq 'dump' and $Options{'p'}) {
|
if ($Options{'o'} eq 'dump' and $Options{'p'}) {
|
||||||
$StartMonth = $EndMonth;
|
$StartMonth = $EndMonth;
|
||||||
warn ("$MySelf: W: You cannot combine time periods (-p) with '-o dump'. Month was set to $StartMonth.\n");
|
warn ("$MySelf: W: You cannot combine time periods (-p) with '-o dump'. Month was set to $StartMonth.\n");
|
||||||
};
|
};
|
||||||
|
|
||||||
### init database
|
### init database
|
||||||
my $DBHandle = InitDB(\%Conf,1);
|
my $DBHandle = InitDB(\%Conf,1);
|
||||||
|
|
||||||
### create report
|
### create report
|
||||||
# get list of newsgroups (-n)
|
# get list of newsgroups (-n)
|
||||||
my ($QueryPart,@GroupList);
|
my ($QueryPart,@GroupList);
|
||||||
my $Newsgroups = $Options{'n'};
|
my $Newsgroups = $Options{'n'};
|
||||||
if ($Newsgroups) {
|
if ($Newsgroups) {
|
||||||
# explode list of newsgroups for WHERE clause
|
# explode list of newsgroups for WHERE clause
|
||||||
($QueryPart,@GroupList) = &SQLGroupList($Newsgroups);
|
($QueryPart,@GroupList) = &SQLGroupList($Newsgroups);
|
||||||
} else {
|
} else {
|
||||||
# set to dummy value (always true)
|
# set to dummy value (always true)
|
||||||
$QueryPart = 1;
|
$QueryPart = 1;
|
||||||
};
|
};
|
||||||
|
|
||||||
# manage thresholds
|
# manage thresholds
|
||||||
if (defined($Options{'t'})) {
|
if (defined($Options{'t'})) {
|
||||||
if ($Options{'i'}) {
|
if ($Options{'i'}) {
|
||||||
# -i: list groups below threshold
|
# -i: list groups below threshold
|
||||||
$QueryPart .= ' AND postings < ?';
|
$QueryPart .= ' AND postings < ?';
|
||||||
} else {
|
} else {
|
||||||
# default: list groups above threshold
|
# default: list groups above threshold
|
||||||
$QueryPart .= ' AND postings > ?';
|
$QueryPart .= ' AND postings > ?';
|
||||||
};
|
};
|
||||||
# push threshold to GroupList to match number of binding vars for DBQuery->execute
|
# push threshold to GroupList to match number of binding vars for DBQuery->execute
|
||||||
push @GroupList,$Options{'t'};
|
push @GroupList,$Options{'t'};
|
||||||
}
|
}
|
||||||
|
|
||||||
# construct WHERE clause
|
# construct WHERE clause
|
||||||
# $QueryPart is "list of newsgroup" (or 1),
|
# $QueryPart is "list of newsgroup" (or 1),
|
||||||
# &SQLHierarchies() takes care of the exclusion of hierarchy levels (.ALL)
|
# &SQLHierarchies() takes care of the exclusion of hierarchy levels (.ALL)
|
||||||
# according to setting of -s
|
# according to setting of -s
|
||||||
my $WhereClause = sprintf('month BETWEEN ? AND ? AND %s %s',$QueryPart,&SQLHierarchies($Options{'s'}));
|
my $WhereClause = sprintf('month BETWEEN ? AND ? AND %s %s',$QueryPart,&SQLHierarchies($Options{'s'}));
|
||||||
|
|
||||||
# get lenght of longest newsgroup delivered by query for formatting purposes
|
# get lenght of longest newsgroup delivered by query for formatting purposes
|
||||||
# FIXME
|
# FIXME
|
||||||
my $MaxLength = &GetMaxLenght($DBHandle,$Conf{'DBTableGrps'},'newsgroup',$WhereClause,$StartMonth,$EndMonth,@GroupList);
|
my $MaxLength = &GetMaxLenght($DBHandle,$Conf{'DBTableGrps'},'newsgroup',$WhereClause,$StartMonth,$EndMonth,@GroupList);
|
||||||
|
|
||||||
my ($OrderClause,$DBQuery);
|
my ($OrderClause,$DBQuery);
|
||||||
# -b (best of / top list) defined?
|
# -b (best of / top list) defined?
|
||||||
if (!defined($Options{'b'}) and !defined($Options{'l'})) {
|
if (!defined($Options{'b'}) and !defined($Options{'l'})) {
|
||||||
# default: neither -b nor -l
|
# default: neither -b nor -l
|
||||||
# set ordering (ORDER BY) to "newsgroups" or "postings", "ASC" or "DESC"
|
# set ordering (ORDER BY) to "newsgroups" or "postings", "ASC" or "DESC"
|
||||||
# according to -q and -d
|
# according to -q and -d
|
||||||
$OrderClause = 'newsgroup';
|
$OrderClause = 'newsgroup';
|
||||||
$OrderClause = 'postings' if $Options{'q'};
|
$OrderClause = 'postings' if $Options{'q'};
|
||||||
$OrderClause .= ' DESC' if $Options{'d'};
|
$OrderClause .= ' DESC' if $Options{'d'};
|
||||||
# prepare query: get number of postings per group from groups table for given months and newsgroups
|
# prepare query: get number of postings per group from groups table for given months and newsgroups
|
||||||
$DBQuery = $DBHandle->prepare(sprintf("SELECT month,newsgroup,postings FROM %s.%s WHERE %s ORDER BY month,%s",$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$WhereClause,$OrderClause));
|
$DBQuery = $DBHandle->prepare(sprintf("SELECT month,newsgroup,postings FROM %s.%s WHERE %s ORDER BY month,%s",$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$WhereClause,$OrderClause));
|
||||||
} elsif ($Options{'b'}) {
|
} elsif ($Options{'b'}) {
|
||||||
# -b is set (then -l can't be!)
|
# -b is set (then -l can't be!)
|
||||||
# set sorting order (-i)
|
# set sorting order (-i)
|
||||||
if ($Options{'i'}) {
|
if ($Options{'i'}) {
|
||||||
$OrderClause = 'postings';
|
$OrderClause = 'postings';
|
||||||
} else {
|
} else {
|
||||||
$OrderClause = 'postings DESC';
|
$OrderClause = 'postings DESC';
|
||||||
};
|
};
|
||||||
# push LIMIT to GroupList to match number of binding vars for DBQuery->execute
|
# push LIMIT to GroupList to match number of binding vars for DBQuery->execute
|
||||||
push @GroupList,$Options{'b'};
|
push @GroupList,$Options{'b'};
|
||||||
# prepare query: get sum of postings per group from groups table for given months and newsgroups with LIMIT
|
# prepare query: get sum of postings per group from groups table for given months and newsgroups with LIMIT
|
||||||
$DBQuery = $DBHandle->prepare(sprintf("SELECT newsgroup,SUM(postings) AS postings FROM %s.%s WHERE %s GROUP BY newsgroup ORDER BY %s,newsgroup LIMIT ?",$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$WhereClause,$OrderClause));
|
$DBQuery = $DBHandle->prepare(sprintf("SELECT newsgroup,SUM(postings) AS postings FROM %s.%s WHERE %s GROUP BY newsgroup ORDER BY %s,newsgroup LIMIT ?",$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$WhereClause,$OrderClause));
|
||||||
} else {
|
} else {
|
||||||
# -l must be set now, as all other cases have been taken care of
|
# -l must be set now, as all other cases have been taken care of
|
||||||
# set sorting order (-i)
|
# set sorting order (-i)
|
||||||
if ($Options{'i'}) {
|
if ($Options{'i'}) {
|
||||||
$OrderClause = '<';
|
$OrderClause = '<';
|
||||||
} else {
|
} else {
|
||||||
$OrderClause = '>';
|
$OrderClause = '>';
|
||||||
};
|
};
|
||||||
# push level and $StartMonth,$EndMonth - again - to GroupList to match number of binding vars for DBQuery->execute
|
# push level and $StartMonth,$EndMonth - again - to GroupList to match number of binding vars for DBQuery->execute
|
||||||
# FIXME -- together with the query (see below)
|
# FIXME -- together with the query (see below)
|
||||||
push @GroupList,$Options{'l'};
|
push @GroupList,$Options{'l'};
|
||||||
push @GroupList,$StartMonth,$EndMonth;
|
push @GroupList,$StartMonth,$EndMonth;
|
||||||
# prepare query: get number of postings per group from groups table for given months and
|
# prepare query: get number of postings per group from groups table for given months and
|
||||||
# FIXME -- this query is ... in dire need of impromevent
|
# FIXME -- this query is ... in dire need of impromevent
|
||||||
$DBQuery = $DBHandle->prepare(sprintf("SELECT month,newsgroup,postings FROM %s.%s WHERE newsgroup IN (SELECT newsgroup FROM %s.%s WHERE %s GROUP BY newsgroup HAVING MAX(postings) %s ?) AND %s ORDER BY newsgroup,month",$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$WhereClause,$OrderClause,$WhereClause));
|
$DBQuery = $DBHandle->prepare(sprintf("SELECT month,newsgroup,postings FROM %s.%s WHERE newsgroup IN (SELECT newsgroup FROM %s.%s WHERE %s GROUP BY newsgroup HAVING MAX(postings) %s ?) AND %s ORDER BY newsgroup,month",$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$WhereClause,$OrderClause,$WhereClause));
|
||||||
};
|
};
|
||||||
|
|
||||||
# execute query
|
# execute query
|
||||||
$DBQuery->execute($StartMonth,$EndMonth,@GroupList)
|
$DBQuery->execute($StartMonth,$EndMonth,@GroupList)
|
||||||
or die sprintf("$MySelf: E: Can't get groups data for %s to %s from %s.%s: %s\n",$StartMonth,$EndMonth,$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$DBI::errstr);
|
or die sprintf("$MySelf: E: Can't get groups data for %s to %s from %s.%s: %s\n",$StartMonth,$EndMonth,$Conf{'DBDatabase'},$Conf{'DBTableGrps'},$DBI::errstr);
|
||||||
|
|
||||||
# output results
|
# output results
|
||||||
# print caption (-c) with time period if -m or -p is set
|
# print caption (-c) with time period if -m or -p is set
|
||||||
# FIXME - month or period should handled differently
|
# FIXME - month or period should handled differently
|
||||||
printf ("----- Report from %s to %s\n",$StartMonth,$EndMonth) if $Options{'c'} and ($Options{'m'} or $Options{'p'});
|
printf ("----- Report from %s to %s\n",$StartMonth,$EndMonth) if $Options{'c'} and ($Options{'m'} or $Options{'p'});
|
||||||
# print caption (-c) with newsgroup list if -n is set
|
# print caption (-c) with newsgroup list if -n is set
|
||||||
printf ("----- Newsgroups: %s\n",join(',',split(/:/,$Newsgroups))) if $Options{'c'} and $Options{'n'};
|
printf ("----- Newsgroups: %s\n",join(',',split(/:/,$Newsgroups))) if $Options{'c'} and $Options{'n'};
|
||||||
# print caption (-c) with threshold if -t is set, taking -i in account
|
# print caption (-c) with threshold if -t is set, taking -i in account
|
||||||
printf ("----- Threshold: %s %u\n",$Options{'i'} ? '<' : '>',$Options{'t'}) if $Options{'c'} and $Options{'t'};
|
printf ("----- Threshold: %s %u\n",$Options{'i'} ? '<' : '>',$Options{'t'}) if $Options{'c'} and $Options{'t'};
|
||||||
if (!defined($Options{'b'}) and !defined($Options{'l'})) {
|
if (!defined($Options{'b'}) and !defined($Options{'l'})) {
|
||||||
# default: neither -b nor -l
|
# default: neither -b nor -l
|
||||||
&OutputData($Options{'o'},$DBQuery,$MaxLength);
|
&OutputData($Options{'o'},$DBQuery,$MaxLength);
|
||||||
} elsif ($Options{'b'}) {
|
} elsif ($Options{'b'}) {
|
||||||
# -b is set (then -l can't be!)
|
# -b is set (then -l can't be!)
|
||||||
# we have to read in the query results ourselves, as they do not have standard layout
|
# we have to read in the query results ourselves, as they do not have standard layout
|
||||||
while (my ($Newsgroup,$Postings) = $DBQuery->fetchrow_array) {
|
while (my ($Newsgroup,$Postings) = $DBQuery->fetchrow_array) {
|
||||||
# we just assign "top x" or "bottom x" instead of a month for the caption
|
# we just assign "top x" or "bottom x" instead of a month for the caption
|
||||||
# FIXME
|
# FIXME
|
||||||
print &FormatOutput($Options{'o'}, ($Options{'i'} ? 'Bottom ' : 'Top ').$Options{'b'}, $Newsgroup, $Postings, $MaxLength);
|
print &FormatOutput($Options{'o'}, ($Options{'i'} ? 'Bottom ' : 'Top ').$Options{'b'}, $Newsgroup, $Postings, $MaxLength);
|
||||||
};
|
};
|
||||||
} else {
|
} else {
|
||||||
# -l must be set now, as all other cases have been taken care of
|
# -l must be set now, as all other cases have been taken care of
|
||||||
# we have to read in the query results ourselves, as they do not have standard layout
|
# we have to read in the query results ourselves, as they do not have standard layout
|
||||||
while (my ($Month,$Newsgroup,$Postings) = $DBQuery->fetchrow_array) {
|
while (my ($Month,$Newsgroup,$Postings) = $DBQuery->fetchrow_array) {
|
||||||
# we just switch $Newsgroups and $Month for output generation
|
# we just switch $Newsgroups and $Month for output generation
|
||||||
# FIXME
|
# FIXME
|
||||||
print &FormatOutput($Options{'o'}, $Newsgroup, $Month, $Postings, 7);
|
print &FormatOutput($Options{'o'}, $Newsgroup, $Month, $Postings, 7);
|
||||||
};
|
};
|
||||||
};
|
};
|
||||||
|
|
||||||
### close handles
|
### close handles
|
||||||
$DBHandle->disconnect;
|
$DBHandle->disconnect;
|
||||||
|
|
||||||
__END__
|
__END__
|
||||||
|
|
||||||
################################ Documentation #################################
|
################################ Documentation #################################
|
||||||
|
|
||||||
=head1 NAME
|
=head1 NAME
|
||||||
|
|
||||||
groupstats - create reports on newsgroup usage
|
groupstats - create reports on newsgroup usage
|
||||||
|
|
||||||
=head1 SYNOPSIS
|
=head1 SYNOPSIS
|
||||||
|
|
||||||
B<groupstats> [B<-Vhiscqd>] [B<-m> I<YYYY-MM>] [B<-p> I<YYYY-MM:YYYY-MM>] [B<-n> I<newsgroup(s)>] [B<-t> I<threshold>] [B<-l> I<level>] [B<-b> I<number>] [B<-o> I<output type>] [B<-g> I<database table>]
|
B<groupstats> [B<-Vhiscqd>] [B<-m> I<YYYY-MM>] [B<-p> I<YYYY-MM:YYYY-MM>] [B<-n> I<newsgroup(s)>] [B<-t> I<threshold>] [B<-l> I<level>] [B<-b> I<number>] [B<-o> I<output type>] [B<-g> I<database table>]
|
||||||
|
|
||||||
=head1 REQUIREMENTS
|
=head1 REQUIREMENTS
|
||||||
|
|
||||||
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
Config::Auto
|
Config::Auto
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
DBI
|
DBI
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 DESCRIPTION
|
=head1 DESCRIPTION
|
||||||
|
|
||||||
This script create reports on newsgroup usage (number of postings per
|
This script create reports on newsgroup usage (number of postings per
|
||||||
group per month) taken from result tables created by
|
group per month) taken from result tables created by
|
||||||
F<gatherstats.pl>.
|
F<gatherstats.pl>.
|
||||||
|
|
||||||
The time period to act on defaults to last month; you can assign
|
The time period to act on defaults to last month; you can assign
|
||||||
another month via the B<-m> switch or a time period via the B<-p>
|
another month via the B<-m> switch or a time period via the B<-p>
|
||||||
switch; the latter takes preference.
|
switch; the latter takes preference.
|
||||||
|
|
||||||
B<groupstats> will process all newsgroups by default; you can limit
|
B<groupstats> will process all newsgroups by default; you can limit
|
||||||
that to only some newsgroups by supplying a list of those groups via
|
that to only some newsgroups by supplying a list of those groups via
|
||||||
B<-n> (see below). You can include hierarchy levels in the output by
|
B<-n> (see below). You can include hierarchy levels in the output by
|
||||||
adding the B<-s> switch (see below).
|
adding the B<-s> switch (see below).
|
||||||
|
|
||||||
Furthermore you can set a threshold via B<-t> so that only newsgroups
|
Furthermore you can set a threshold via B<-t> so that only newsgroups
|
||||||
with more postings per month will be included in the report. You can
|
with more postings per month will be included in the report. You can
|
||||||
invert that by the B<-i> switch so only newsgroups with less than
|
invert that by the B<-i> switch so only newsgroups with less than
|
||||||
I<threshold> postings per month will be included.
|
I<threshold> postings per month will be included.
|
||||||
|
|
||||||
You can sort the output by number of postings per month instead of the
|
You can sort the output by number of postings per month instead of the
|
||||||
default (alphabetical list of newsgroups) by using B<-q>; you can
|
default (alphabetical list of newsgroups) by using B<-q>; you can
|
||||||
reverse the sorting order (from highest to lowest or in reversed
|
reverse the sorting order (from highest to lowest or in reversed
|
||||||
alphabetical order) by using B<-d>.
|
alphabetical order) by using B<-d>.
|
||||||
|
|
||||||
Furthermore, you can create a list of newsgroups that had consistently
|
Furthermore, you can create a list of newsgroups that had consistently
|
||||||
more (or less) than x postings per month during the whole report
|
more (or less) than x postings per month during the whole report
|
||||||
period by using B<-l> (together with B<i> as needed).
|
period by using B<-l> (together with B<i> as needed).
|
||||||
|
|
||||||
Last but not least you can create a "best of" list of the top x
|
Last but not least you can create a "best of" list of the top x
|
||||||
newsgroups via B<-b> (or a "worst of" list by adding B<i>).
|
newsgroups via B<-b> (or a "worst of" list by adding B<i>).
|
||||||
|
|
||||||
By default, B<groupstats> will dump a very simple alphabetical list of
|
By default, B<groupstats> will dump a very simple alphabetical list of
|
||||||
newsgroups, one per line, followed by the number of postings in that
|
newsgroups, one per line, followed by the number of postings in that
|
||||||
month. This output format of course cannot sensibly be combined with
|
month. This output format of course cannot sensibly be combined with
|
||||||
time periods, so you can set the output format by using B<-o> (see
|
time periods, so you can set the output format by using B<-o> (see
|
||||||
below). Captions can be added by setting the B<-c> switch.
|
below). Captions can be added by setting the B<-c> switch.
|
||||||
|
|
||||||
=head2 Configuration
|
=head2 Configuration
|
||||||
|
|
||||||
F<groupstats.pl> will read its configuration from F<newsstats.conf>
|
F<groupstats.pl> will read its configuration from F<newsstats.conf>
|
||||||
which should be present in the same directory via Config::Auto.
|
which should be present in the same directory via Config::Auto.
|
||||||
|
|
||||||
See doc/INSTALL for an overview of possible configuration options.
|
See doc/INSTALL for an overview of possible configuration options.
|
||||||
|
|
||||||
You can override configuration options via the B<-g> switch.
|
You can override configuration options via the B<-g> switch.
|
||||||
|
|
||||||
=head1 OPTIONS
|
=head1 OPTIONS
|
||||||
|
|
||||||
=over 3
|
=over 3
|
||||||
|
|
||||||
=item B<-V> (version)
|
=item B<-V> (version)
|
||||||
|
|
||||||
Print out version and copyright information on B<yapfaq> and exit.
|
Print out version and copyright information on B<yapfaq> and exit.
|
||||||
|
|
||||||
=item B<-h> (help)
|
=item B<-h> (help)
|
||||||
|
|
||||||
Print this man page and exit.
|
Print this man page and exit.
|
||||||
|
|
||||||
=item B<-m> I<YYYY-MM> (month)
|
=item B<-m> I<YYYY-MM> (month)
|
||||||
|
|
||||||
Set processing period to a month in YYYY-MM format. Ignored if B<-p>
|
Set processing period to a month in YYYY-MM format. Ignored if B<-p>
|
||||||
is set.
|
is set.
|
||||||
|
|
||||||
=item B<-p> I<YYYY-MM:YYYY-MM> (period)
|
=item B<-p> I<YYYY-MM:YYYY-MM> (period)
|
||||||
|
|
||||||
Set processing period to a time period between two month, each in
|
Set processing period to a time period between two month, each in
|
||||||
YYYY-MM format, separated by a colon. Overrides B<-m>.
|
YYYY-MM format, separated by a colon. Overrides B<-m>.
|
||||||
|
|
||||||
=item B<-n> I<newsgroup(s)> (newsgroups)
|
=item B<-n> I<newsgroup(s)> (newsgroups)
|
||||||
|
|
||||||
Limit processing to a certain set of newsgroups. I<newsgroup(s)> can
|
Limit processing to a certain set of newsgroups. I<newsgroup(s)> can
|
||||||
be a single newsgroup name (de.alt.test), a newsgroup hierarchy
|
be a single newsgroup name (de.alt.test), a newsgroup hierarchy
|
||||||
(de.alt.*) or a list of either of these, separated by colons, for
|
(de.alt.*) or a list of either of these, separated by colons, for
|
||||||
example
|
example
|
||||||
|
|
||||||
de.test:de.alt.test:de.newusers.*
|
de.test:de.alt.test:de.newusers.*
|
||||||
|
|
||||||
=item B<-t> I<threshold> (threshold)
|
=item B<-t> I<threshold> (threshold)
|
||||||
|
|
||||||
Only include newsgroups with more than I<threshold> postings per
|
Only include newsgroups with more than I<threshold> postings per
|
||||||
month. Can be inverted by the B<-i> switch so that only newsgroups
|
month. Can be inverted by the B<-i> switch so that only newsgroups
|
||||||
with less than I<threshold> postings will be included.
|
with less than I<threshold> postings will be included.
|
||||||
|
|
||||||
This setting will be ignored if B<-l> or B<-b> is set.
|
This setting will be ignored if B<-l> or B<-b> is set.
|
||||||
|
|
||||||
=item B<-l> I<level> (level)
|
=item B<-l> I<level> (level)
|
||||||
|
|
||||||
Only include newsgroups with more than I<level> postings per
|
Only include newsgroups with more than I<level> postings per
|
||||||
month, every month during the whole reporting period. Can be inverted
|
month, every month during the whole reporting period. Can be inverted
|
||||||
by the B<-i> switch so that only newsgroups with less than I<level>
|
by the B<-i> switch so that only newsgroups with less than I<level>
|
||||||
postings every single month will be included. Output will be ordered
|
postings every single month will be included. Output will be ordered
|
||||||
by newsgroup name, followed by month.
|
by newsgroup name, followed by month.
|
||||||
|
|
||||||
This setting will be ignored if B<-b> is set. Overrides B<-t> and
|
This setting will be ignored if B<-b> is set. Overrides B<-t> and
|
||||||
can't be used together with B<-q> or B<-d>.
|
can't be used together with B<-q> or B<-d>.
|
||||||
|
|
||||||
=item B<-b> I<n> (best of)
|
=item B<-b> I<n> (best of)
|
||||||
|
|
||||||
Create a list of the I<n> newsgroups with the most postings over the
|
Create a list of the I<n> newsgroups with the most postings over the
|
||||||
whole reporting period. Can be inverted by the B<-i> switch so that a
|
whole reporting period. Can be inverted by the B<-i> switch so that a
|
||||||
list of the I<n> newsgroups with the least postings over the whole
|
list of the I<n> newsgroups with the least postings over the whole
|
||||||
period is generated. Output will be ordered by sum of postings.
|
period is generated. Output will be ordered by sum of postings.
|
||||||
|
|
||||||
Overrides B<-t> and B<-l> and can't be used together with B<-q> or
|
Overrides B<-t> and B<-l> and can't be used together with B<-q> or
|
||||||
B<-d>. Output format is set to I<pretty> (see below).
|
B<-d>. Output format is set to I<pretty> (see below).
|
||||||
|
|
||||||
=item B<-i> (invert)
|
=item B<-i> (invert)
|
||||||
|
|
||||||
Used in conjunction with B<-t>, B<-l> or B<-b> to set a lower
|
Used in conjunction with B<-t>, B<-l> or B<-b> to set a lower
|
||||||
threshold or level or generate a "bottom list" instead of a top list.
|
threshold or level or generate a "bottom list" instead of a top list.
|
||||||
|
|
||||||
=item B<-s> (sum per hierarchy level)
|
=item B<-s> (sum per hierarchy level)
|
||||||
|
|
||||||
Include "virtual" groups for every hierarchy level in output, for
|
Include "virtual" groups for every hierarchy level in output, for
|
||||||
example:
|
example:
|
||||||
|
|
||||||
de.alt.ALL 10
|
de.alt.ALL 10
|
||||||
de.alt.test 5
|
de.alt.test 5
|
||||||
de.alt.admin 7
|
de.alt.admin 7
|
||||||
|
|
||||||
See the B<gatherstats> man page for details.
|
See the B<gatherstats> man page for details.
|
||||||
|
|
||||||
=item B<-o> I<output type> (output format)
|
=item B<-o> I<output type> (output format)
|
||||||
|
|
||||||
Set output format. Default is I<dump>, consisting of an alphabetical
|
Set output format. Default is I<dump>, consisting of an alphabetical
|
||||||
list of newsgroups, each on a new line, followed by the number of
|
list of newsgroups, each on a new line, followed by the number of
|
||||||
postings in that month. This default format can't be used with time
|
postings in that month. This default format can't be used with time
|
||||||
periods of more than one month.
|
periods of more than one month.
|
||||||
|
|
||||||
I<list> format is like I<dump>, but will print the month in front of
|
I<list> format is like I<dump>, but will print the month in front of
|
||||||
the newsgroup name.
|
the newsgroup name.
|
||||||
|
|
||||||
I<dumpgroup> format can only be use with a group list (see B<-n>) of
|
I<dumpgroup> format can only be use with a group list (see B<-n>) of
|
||||||
exactly one newsgroup and is like I<dump>, but will output months,
|
exactly one newsgroup and is like I<dump>, but will output months,
|
||||||
followed by the number of postings.
|
followed by the number of postings.
|
||||||
|
|
||||||
If you don't need easily parsable output, you'll mostly use I<pretty>
|
If you don't need easily parsable output, you'll mostly use I<pretty>
|
||||||
format, which will print a header for each new month and try to align
|
format, which will print a header for each new month and try to align
|
||||||
newsgroup names and posting counts. Usage of B<-b> will force this
|
newsgroup names and posting counts. Usage of B<-b> will force this
|
||||||
format.
|
format.
|
||||||
|
|
||||||
=item B<-c> (captions)
|
=item B<-c> (captions)
|
||||||
|
|
||||||
Add captions to output (reporting period, newsgroups list, threshold).
|
Add captions to output (reporting period, newsgroups list, threshold).
|
||||||
|
|
||||||
=item B<-q> (quantity of postings)
|
=item B<-q> (quantity of postings)
|
||||||
|
|
||||||
Sort by number of postings instead of by newsgroup names.
|
Sort by number of postings instead of by newsgroup names.
|
||||||
|
|
||||||
Cannot be used with B<-l> or B<-b>.
|
Cannot be used with B<-l> or B<-b>.
|
||||||
|
|
||||||
=item B<-d> (descending)
|
=item B<-d> (descending)
|
||||||
|
|
||||||
Change sort order to descending.
|
Change sort order to descending.
|
||||||
|
|
||||||
Cannot be used with B<-l> or B<-b>.
|
Cannot be used with B<-l> or B<-b>.
|
||||||
|
|
||||||
=item B<-g> I<table> (postings per group table)
|
=item B<-g> I<table> (postings per group table)
|
||||||
|
|
||||||
Override I<DBTableGrps> from F<newsstats.conf>.
|
Override I<DBTableGrps> from F<newsstats.conf>.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 INSTALLATION
|
=head1 INSTALLATION
|
||||||
|
|
||||||
See doc/INSTALL.
|
See doc/INSTALL.
|
||||||
|
|
||||||
=head1 EXAMPLES
|
=head1 EXAMPLES
|
||||||
|
|
||||||
Show number of postings per group for lasth month in I<dump> format:
|
Show number of postings per group for lasth month in I<dump> format:
|
||||||
|
|
||||||
groupstats
|
groupstats
|
||||||
|
|
||||||
Show that report for January of 2010 and de.alt.* plus de.test,
|
Show that report for January of 2010 and de.alt.* plus de.test,
|
||||||
including display of hierarchy levels:
|
including display of hierarchy levels:
|
||||||
|
|
||||||
groupstats -m 2010-01 -n de.alt.*:de.test -s
|
groupstats -m 2010-01 -n de.alt.*:de.test -s
|
||||||
|
|
||||||
Show that report for the year of 2010 in I<pretty> format:
|
Show that report for the year of 2010 in I<pretty> format:
|
||||||
|
|
||||||
groupstats -p 2010-01:2010-12 -o pretty
|
groupstats -p 2010-01:2010-12 -o pretty
|
||||||
|
|
||||||
Only show newsgroups with less than 30 postings last month, ordered
|
Only show newsgroups with less than 30 postings last month, ordered
|
||||||
by number of postings, descending, in I<pretty> format:
|
by number of postings, descending, in I<pretty> format:
|
||||||
|
|
||||||
groupstats -iqdt 30 -o pretty
|
groupstats -iqdt 30 -o pretty
|
||||||
|
|
||||||
Show top 10 for the first half-year of of 2010 in I<pretty> format:
|
Show top 10 for the first half-year of of 2010 in I<pretty> format:
|
||||||
|
|
||||||
groupstats -p 2010-01:2010-06 -b 10 -o pretty
|
groupstats -p 2010-01:2010-06 -b 10 -o pretty
|
||||||
|
|
||||||
Report all groups that had less than 30 postings every singele month
|
Report all groups that had less than 30 postings every singele month
|
||||||
in the year of 2010 (I<pretty> format is forced)
|
in the year of 2010 (I<pretty> format is forced)
|
||||||
|
|
||||||
groupstats -p 2010-01:2010-12 -il 30
|
groupstats -p 2010-01:2010-12 -il 30
|
||||||
|
|
||||||
=head1 FILES
|
=head1 FILES
|
||||||
|
|
||||||
=over 4
|
=over 4
|
||||||
|
|
||||||
=item F<groupstats.pl>
|
=item F<groupstats.pl>
|
||||||
|
|
||||||
The script itself.
|
The script itself.
|
||||||
|
|
||||||
=item F<NewsStats.pm>
|
=item F<NewsStats.pm>
|
||||||
|
|
||||||
Library functions for the NewsStats package.
|
Library functions for the NewsStats package.
|
||||||
|
|
||||||
=item F<newsstats.conf>
|
=item F<newsstats.conf>
|
||||||
|
|
||||||
Runtime configuration file for B<yapfaq>.
|
Runtime configuration file for B<yapfaq>.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 BUGS
|
=head1 BUGS
|
||||||
|
|
||||||
Please report any bugs or feature requests to the author or use the
|
Please report any bugs or feature requests to the author or use the
|
||||||
bug tracker at L<http://bugs.th-h.de/>!
|
bug tracker at L<http://bugs.th-h.de/>!
|
||||||
|
|
||||||
=head1 SEE ALSO
|
=head1 SEE ALSO
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/README
|
doc/README
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/INSTALL
|
doc/INSTALL
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
gatherstats -h
|
gatherstats -h
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
This script is part of the B<NewsStats> package.
|
This script is part of the B<NewsStats> package.
|
||||||
|
|
||||||
=head1 AUTHOR
|
=head1 AUTHOR
|
||||||
|
|
||||||
Thomas Hochstein <thh@inter.net>
|
Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
=head1 COPYRIGHT AND LICENSE
|
=head1 COPYRIGHT AND LICENSE
|
||||||
|
|
||||||
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
This program is free software; you may redistribute it and/or modify it
|
This program is free software; you may redistribute it and/or modify it
|
||||||
under the same terms as Perl itself.
|
under the same terms as Perl itself.
|
||||||
|
|
||||||
=cut
|
=cut
|
||||||
|
|
|
||||||
|
|
@ -1,257 +1,257 @@
|
||||||
#! /usr/bin/perl -W
|
#! /usr/bin/perl -W
|
||||||
#
|
#
|
||||||
# install.pl
|
# install.pl
|
||||||
#
|
#
|
||||||
# This script will create database tables as necessary.
|
# This script will create database tables as necessary.
|
||||||
#
|
#
|
||||||
# It is part of the NewsStats package.
|
# It is part of the NewsStats package.
|
||||||
#
|
#
|
||||||
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
# Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
#
|
#
|
||||||
# It can be redistributed and/or modified under the same terms under
|
# It can be redistributed and/or modified under the same terms under
|
||||||
# which Perl itself is published.
|
# which Perl itself is published.
|
||||||
|
|
||||||
BEGIN {
|
BEGIN {
|
||||||
our $VERSION = "0.01";
|
our $VERSION = "0.01";
|
||||||
use File::Basename;
|
use File::Basename;
|
||||||
# we're in .../install, so our module is in ..
|
# we're in .../install, so our module is in ..
|
||||||
push(@INC, dirname($0).'/..');
|
push(@INC, dirname($0).'/..');
|
||||||
}
|
}
|
||||||
use strict;
|
use strict;
|
||||||
|
|
||||||
use NewsStats qw(:DEFAULT);
|
use NewsStats qw(:DEFAULT);
|
||||||
|
|
||||||
use Cwd;
|
use Cwd;
|
||||||
|
|
||||||
use DBI;
|
use DBI;
|
||||||
|
|
||||||
################################# Main program #################################
|
################################# Main program #################################
|
||||||
|
|
||||||
### read commandline options
|
### read commandline options
|
||||||
my %Options = &ReadOptions('');
|
my %Options = &ReadOptions('');
|
||||||
|
|
||||||
### change working directory to .. (as we're in .../install)
|
### change working directory to .. (as we're in .../install)
|
||||||
chdir dirname($0).'/..';
|
chdir dirname($0).'/..';
|
||||||
|
|
||||||
### read configuration
|
### read configuration
|
||||||
print("Reading configuration.\n");
|
print("Reading configuration.\n");
|
||||||
my %Conf = %{ReadConfig('newsstats.conf')};
|
my %Conf = %{ReadConfig('newsstats.conf')};
|
||||||
|
|
||||||
##### --------------------------------------------------------------------------
|
##### --------------------------------------------------------------------------
|
||||||
##### Database table definitions
|
##### Database table definitions
|
||||||
##### --------------------------------------------------------------------------
|
##### --------------------------------------------------------------------------
|
||||||
|
|
||||||
my %DBCreate = ('DBTableRaw' => <<RAW, 'DBTableGrps' => <<GRPS);
|
my %DBCreate = ('DBTableRaw' => <<RAW, 'DBTableGrps' => <<GRPS);
|
||||||
--
|
--
|
||||||
-- Table structure for table DBTableRaw
|
-- Table structure for table DBTableRaw
|
||||||
--
|
--
|
||||||
|
|
||||||
CREATE TABLE IF NOT EXISTS `$Conf{'DBTableRaw'}` (
|
CREATE TABLE IF NOT EXISTS `$Conf{'DBTableRaw'}` (
|
||||||
`id` bigint(20) unsigned NOT NULL auto_increment,
|
`id` bigint(20) unsigned NOT NULL auto_increment,
|
||||||
`day` date NOT NULL,
|
`day` date NOT NULL,
|
||||||
`mid` varchar(250) character set ascii NOT NULL,
|
`mid` varchar(250) character set ascii NOT NULL,
|
||||||
`date` datetime NOT NULL,
|
`date` datetime NOT NULL,
|
||||||
`timestamp` bigint(20) NOT NULL,
|
`timestamp` bigint(20) NOT NULL,
|
||||||
`token` varchar(80) character set ascii NOT NULL,
|
`token` varchar(80) character set ascii NOT NULL,
|
||||||
`size` bigint(20) NOT NULL,
|
`size` bigint(20) NOT NULL,
|
||||||
`peer` varchar(250) NOT NULL,
|
`peer` varchar(250) NOT NULL,
|
||||||
`path` varchar(1000) NOT NULL,
|
`path` varchar(1000) NOT NULL,
|
||||||
`newsgroups` varchar(1000) NOT NULL,
|
`newsgroups` varchar(1000) NOT NULL,
|
||||||
`headers` longtext NOT NULL,
|
`headers` longtext NOT NULL,
|
||||||
`disregard` tinyint(1) default '0',
|
`disregard` tinyint(1) default '0',
|
||||||
PRIMARY KEY (`id`),
|
PRIMARY KEY (`id`),
|
||||||
KEY `day` (`day`),
|
KEY `day` (`day`),
|
||||||
KEY `mid` (`mid`),
|
KEY `mid` (`mid`),
|
||||||
KEY `peer` (`peer`)
|
KEY `peer` (`peer`)
|
||||||
) ENGINE=MyISAM DEFAULT CHARSET=utf8 COMMENT='Raw data';
|
) ENGINE=MyISAM DEFAULT CHARSET=utf8 COMMENT='Raw data';
|
||||||
RAW
|
RAW
|
||||||
--
|
--
|
||||||
-- Table structure for table DBTableGrps
|
-- Table structure for table DBTableGrps
|
||||||
--
|
--
|
||||||
|
|
||||||
CREATE TABLE IF NOT EXISTS `$Conf{'DBTableGrps'}` (
|
CREATE TABLE IF NOT EXISTS `$Conf{'DBTableGrps'}` (
|
||||||
`id` bigint(20) unsigned NOT NULL auto_increment,
|
`id` bigint(20) unsigned NOT NULL auto_increment,
|
||||||
`month` varchar(7) character set ascii NOT NULL,
|
`month` varchar(7) character set ascii NOT NULL,
|
||||||
`newsgroup` varchar(100) NOT NULL,
|
`newsgroup` varchar(100) NOT NULL,
|
||||||
`postings` int(11) NOT NULL,
|
`postings` int(11) NOT NULL,
|
||||||
`revision` timestamp NOT NULL default CURRENT_TIMESTAMP on update CURRENT_TIMESTAMP,
|
`revision` timestamp NOT NULL default CURRENT_TIMESTAMP on update CURRENT_TIMESTAMP,
|
||||||
PRIMARY KEY (`id`),
|
PRIMARY KEY (`id`),
|
||||||
UNIQUE KEY `month_newsgroup` (`month`,`newsgroup`),
|
UNIQUE KEY `month_newsgroup` (`month`,`newsgroup`),
|
||||||
KEY `newsgroup` (`newsgroup`),
|
KEY `newsgroup` (`newsgroup`),
|
||||||
KEY `postings` (`postings`)
|
KEY `postings` (`postings`)
|
||||||
) ENGINE=MyISAM DEFAULT CHARSET=utf8 COMMENT='Postings per newsgroup';
|
) ENGINE=MyISAM DEFAULT CHARSET=utf8 COMMENT='Postings per newsgroup';
|
||||||
GRPS
|
GRPS
|
||||||
|
|
||||||
##### --------------------------- End of definitions ---------------------------
|
##### --------------------------- End of definitions ---------------------------
|
||||||
|
|
||||||
### create database tables
|
### create database tables
|
||||||
print "-----\nStarting database table generation.\n";
|
print "-----\nStarting database table generation.\n";
|
||||||
# DB init
|
# DB init
|
||||||
my $DBHandle = InitDB(\%Conf,1);
|
my $DBHandle = InitDB(\%Conf,1);
|
||||||
|
|
||||||
# read tables
|
# read tables
|
||||||
my %TablesInDB = %{$DBHandle->table_info('%', '%', '%', 'TABLE')->fetchall_hashref('TABLE_NAME')};
|
my %TablesInDB = %{$DBHandle->table_info('%', '%', '%', 'TABLE')->fetchall_hashref('TABLE_NAME')};
|
||||||
|
|
||||||
# check for tables and create them, if they don't exist yet
|
# check for tables and create them, if they don't exist yet
|
||||||
foreach my $Table (keys %DBCreate) {
|
foreach my $Table (keys %DBCreate) {
|
||||||
if (defined($TablesInDB{$Conf{$Table}})) {
|
if (defined($TablesInDB{$Conf{$Table}})) {
|
||||||
printf("Database table %s.%s already exists, skipping ....\n",$Conf{'DBDatabase'},$Conf{$Table});
|
printf("Database table %s.%s already exists, skipping ....\n",$Conf{'DBDatabase'},$Conf{$Table});
|
||||||
next;
|
next;
|
||||||
};
|
};
|
||||||
my $DBQuery = $DBHandle->prepare($DBCreate{$Table});
|
my $DBQuery = $DBHandle->prepare($DBCreate{$Table});
|
||||||
$DBQuery->execute() or die sprintf("$MySelf: E: Can't create table %s in database %s: %s%\n",$Table,$Conf{'DBDatabase'},$DBI::errstr);
|
$DBQuery->execute() or die sprintf("$MySelf: E: Can't create table %s in database %s: %s%\n",$Table,$Conf{'DBDatabase'},$DBI::errstr);
|
||||||
printf("Database table %s.%s created succesfully.\n",$Conf{'DBDatabase'},$Conf{$Table});
|
printf("Database table %s.%s created succesfully.\n",$Conf{'DBDatabase'},$Conf{$Table});
|
||||||
};
|
};
|
||||||
|
|
||||||
# close handle
|
# close handle
|
||||||
$DBHandle->disconnect;
|
$DBHandle->disconnect;
|
||||||
print "Database table generation done.\n";
|
print "Database table generation done.\n";
|
||||||
|
|
||||||
### output information on other necessary steps
|
### output information on other necessary steps
|
||||||
my $Path = cwd();
|
my $Path = cwd();
|
||||||
print <<TODO;
|
print <<TODO;
|
||||||
-----
|
-----
|
||||||
Things left to do:
|
Things left to do:
|
||||||
|
|
||||||
1) Setup an INN feed to feedlog.pl
|
1) Setup an INN feed to feedlog.pl
|
||||||
|
|
||||||
a) Edit your 'newsfeeds' file and insert something like
|
a) Edit your 'newsfeeds' file and insert something like
|
||||||
|
|
||||||
## gather statistics for NewsStats
|
## gather statistics for NewsStats
|
||||||
newsstats!\
|
newsstats!\
|
||||||
:!*,de.*\
|
:!*,de.*\
|
||||||
:Tc,WmtfbsPNH,Ac:$Path/feedlog.pl
|
:Tc,WmtfbsPNH,Ac:$Path/feedlog.pl
|
||||||
|
|
||||||
Please
|
Please
|
||||||
|
|
||||||
* check that you got the path to feedlog.pl right
|
* check that you got the path to feedlog.pl right
|
||||||
* check that feedlog.pl can be executed by the news user
|
* check that feedlog.pl can be executed by the news user
|
||||||
* adapt the pattern (here: 'de.*') to your needs
|
* adapt the pattern (here: 'de.*') to your needs
|
||||||
|
|
||||||
b) Check your 'newsfeeds' syntax:
|
b) Check your 'newsfeeds' syntax:
|
||||||
|
|
||||||
# ctlinnd checkfile
|
# ctlinnd checkfile
|
||||||
|
|
||||||
and reload 'newsfeeds':
|
and reload 'newsfeeds':
|
||||||
|
|
||||||
# ctlinnd reload newsfeeds 'Adding newsstats! feed'
|
# ctlinnd reload newsfeeds 'Adding newsstats! feed'
|
||||||
|
|
||||||
c) Watch your 'news.notice' and 'errlog' files:
|
c) Watch your 'news.notice' and 'errlog' files:
|
||||||
|
|
||||||
# tail -f /var/log/news/news.notice
|
# tail -f /var/log/news/news.notice
|
||||||
...
|
...
|
||||||
# tail -f /var/log/news/errlog
|
# tail -f /var/log/news/errlog
|
||||||
|
|
||||||
2) Watch your $Conf{'DBTableRaw'} table fill.
|
2) Watch your $Conf{'DBTableRaw'} table fill.
|
||||||
|
|
||||||
3) Read the documentation. ;)
|
3) Read the documentation. ;)
|
||||||
|
|
||||||
Enjoy!
|
Enjoy!
|
||||||
|
|
||||||
-thh <thh\@inter.net>
|
-thh <thh\@inter.net>
|
||||||
TODO
|
TODO
|
||||||
|
|
||||||
__END__
|
__END__
|
||||||
|
|
||||||
################################ Documentation #################################
|
################################ Documentation #################################
|
||||||
|
|
||||||
=head1 NAME
|
=head1 NAME
|
||||||
|
|
||||||
install - installation script
|
install - installation script
|
||||||
|
|
||||||
=head1 SYNOPSIS
|
=head1 SYNOPSIS
|
||||||
|
|
||||||
B<install> [B<-Vh>]
|
B<install> [B<-Vh>]
|
||||||
|
|
||||||
=head1 REQUIREMENTS
|
=head1 REQUIREMENTS
|
||||||
|
|
||||||
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
See doc/README: Perl 5.8.x itself and the following modules from CPAN:
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
Config::Auto
|
Config::Auto
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
DBI
|
DBI
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 DESCRIPTION
|
=head1 DESCRIPTION
|
||||||
|
|
||||||
This script will create database tables as necessary and configured.
|
This script will create database tables as necessary and configured.
|
||||||
|
|
||||||
=head2 Configuration
|
=head2 Configuration
|
||||||
|
|
||||||
F<install.pl> will read its configuration from F<newsstats.conf> via
|
F<install.pl> will read its configuration from F<newsstats.conf> via
|
||||||
Config::Auto.
|
Config::Auto.
|
||||||
|
|
||||||
See doc/INSTALL for an overview of possible configuration options.
|
See doc/INSTALL for an overview of possible configuration options.
|
||||||
|
|
||||||
=head1 OPTIONS
|
=head1 OPTIONS
|
||||||
|
|
||||||
=over 3
|
=over 3
|
||||||
|
|
||||||
=item B<-V> (version)
|
=item B<-V> (version)
|
||||||
|
|
||||||
Print out version and copyright information on B<yapfaq> and exit.
|
Print out version and copyright information on B<yapfaq> and exit.
|
||||||
|
|
||||||
=item B<-h> (help)
|
=item B<-h> (help)
|
||||||
|
|
||||||
Print this man page and exit.
|
Print this man page and exit.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 FILES
|
=head1 FILES
|
||||||
|
|
||||||
=over 4
|
=over 4
|
||||||
|
|
||||||
=item F<install.pl>
|
=item F<install.pl>
|
||||||
|
|
||||||
The script itself.
|
The script itself.
|
||||||
|
|
||||||
=item F<NewsStats.pm>
|
=item F<NewsStats.pm>
|
||||||
|
|
||||||
Library functions for the NewsStats package.
|
Library functions for the NewsStats package.
|
||||||
|
|
||||||
=item F<newsstats.conf>
|
=item F<newsstats.conf>
|
||||||
|
|
||||||
Runtime configuration file for B<yapfaq>.
|
Runtime configuration file for B<yapfaq>.
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
=head1 BUGS
|
=head1 BUGS
|
||||||
|
|
||||||
Please report any bugs or feature requests to the author or use the
|
Please report any bugs or feature requests to the author or use the
|
||||||
bug tracker at L<http://bugs.th-h.de/>!
|
bug tracker at L<http://bugs.th-h.de/>!
|
||||||
|
|
||||||
=head1 SEE ALSO
|
=head1 SEE ALSO
|
||||||
|
|
||||||
=over 2
|
=over 2
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/README
|
doc/README
|
||||||
|
|
||||||
=item -
|
=item -
|
||||||
|
|
||||||
doc/INSTALL
|
doc/INSTALL
|
||||||
|
|
||||||
=back
|
=back
|
||||||
|
|
||||||
This script is part of the B<NewsStats> package.
|
This script is part of the B<NewsStats> package.
|
||||||
|
|
||||||
=head1 AUTHOR
|
=head1 AUTHOR
|
||||||
|
|
||||||
Thomas Hochstein <thh@inter.net>
|
Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
=head1 COPYRIGHT AND LICENSE
|
=head1 COPYRIGHT AND LICENSE
|
||||||
|
|
||||||
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
Copyright (c) 2010 Thomas Hochstein <thh@inter.net>
|
||||||
|
|
||||||
This program is free software; you may redistribute it and/or modify it
|
This program is free software; you may redistribute it and/or modify it
|
||||||
under the same terms as Perl itself.
|
under the same terms as Perl itself.
|
||||||
|
|
||||||
=cut
|
=cut
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue